analysis

split train into train and validation

data = read.csv("../Data/train.csv")
test = read.csv("../Data/test.csv")
smp_size <- floor(0.8 * nrow(data))
## set the seed to make your partition reproductible
set.seed(123)
train_ind <- sample(seq_len(nrow(data)), size = smp_size)
train <- data[train_ind, ]
validation <- data[-train_ind, ]

analysis

lattitude , longitude plot

library(ggplot2)
ggplot(data = data) +
  geom_point(aes(x = latitude, y = longitude, color =(interest_level)), alpha = 1)+
    xlim(40.5, 41.0) +
    ylim(-74.05, -73.75)

ggplot(data = data[data["interest_level"] == "low",]) +
  geom_point(aes(x = latitude, y = longitude), alpha = 1)+
    xlim(40.5, 41.0) +
    ylim(-74.05, -73.75)

ggplot(data = data[data["interest_level"] == "medium",]) +
  geom_point(aes(x = latitude, y = longitude), alpha = 1)+
    xlim(40.5, 41.0) +
    ylim(-74.05, -73.75)

ggplot(data = data[data["interest_level"] == "high",]) +
  geom_point(aes(x = latitude, y = longitude), alpha = 1)+
    xlim(40.5, 41.0) +
    ylim(-74.05, -73.75)

lattitude, longitude and

library(plotly)
p <- plot_ly(data[data$longitude > -74 & data$longitude < -73.9 & data$price < 20000,], x = ~latitude, y = ~longitude, z = ~price, color = ~interest_level, colors = c('#BF382A', '#0C4B8E', "#F0E442")) %>%
  add_markers() %>%
  layout(list(   
         xaxis = list( range =c(40, 41), autorange = F),
         yaxis = list( range = c(-74, -73), autorange = F)
         
         
           
        ))
p